Automatic color validation of image metadata

• US 10,255,295 B2
• Filed: 06/26/2014
• Issued: 04/09/2019
• Est. Priority Date: 06/26/2014
• Status: Expired due to Fees

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Gunningham, Sebastian Jorge, Sayre, III, Paul Barnhart, Dorner, Charles Shearer, Haitani, Robert Yuji, Ramos, Gonzalo Alberto
• Primary Examiner(s): Willis, Amanda L
• Application Number:
  US14/315,932
• Publication Number:
  US 20150379001A1
• Time in Patent Office: 1,748 Days
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information

Abstract

Systems and methods are described that validate color information in metadata associated with an image. Color information associated with images, in metadata, may need to be validated because there may be mistakes in the metadata. Color names associated with colors may be based on human generated data or human surveys. Individual colors may be extracted from images, which may be associated with the color names. Furthermore, the color names may be retrieved from a data store via a fast index color search. The color information in the metadata may be validated against the color names.

Claims

1. A system comprising:

a non-transitory computer-readable storage medium configured to store an electronic catalog comprising a plurality of items, wherein each item of the plurality of items is associated with an image and textual data that is descriptive of the item, and wherein the electronic catalog further comprises at least an inaccuracy where some textual data inaccurately describes the item; and

a hardware processor in communication with the non-transitory computer-readable storage medium, the hardware processor configured to execute computer-executable instructions to at least;

receive a first image associated with a first item from the electronic catalog, wherein the first image comprises a first plurality of colors;

retrieve first textual data associated with the first item;

obtain a predetermined color palette comprising a second plurality of colors, the predetermined color palette associated with a second color palette name comprising second textual data;

determine a first color range based at least in part on a color threshold from a first color of the first plurality of colors in a color space, wherein the color space corresponds to a mathematical color model, and wherein the first color within the mathematical color model corresponds to a coordinate;

compare the first color to a second color from the second plurality of colors, based at least in part on the second color being within the first color range, to determine that the first color corresponds to the second color, wherein comparing the first color to the second color further comprises;

calculating an integer search range, wherein calculating the integer search range further comprises interleaving bits from the first color range;

initiating a search of a data store based at least in part on a search query comprising the integer search range as a search parameter, the data store comprising a record associated with at least one indexed integer color value; and

receiving a search result from the data store, the search result comprising a first record associated with a first indexed integer color value for the second color;

compare a third color from the first plurality of colors to a fourth color from the second plurality of colors to determine that the third color corresponds to the fourth color;

identify the inaccuracy, wherein identifying the inaccuracy comprises;

comparing the first textual data and the second color palette name based at least on one of partial textual matching or textual matching of the first textual data and the second textual data to determine a difference between the first textual data and the second palette color name; and

in response to identifying the inaccuracy, update the first textual data of the first item of the electronic catalog to generate updated first textual data.

2. The system of claim 1, wherein the second color palette name corresponds to user input data.

3. The system of claim 1, wherein the hardware processor is further configured to execute computer-executable instructions to at least:

generate a user interface, wherein the user interface is configured to display the first image, the first textual data, and the second color palette name.

4. The system of claim 1, wherein the hardware processor is further configured to execute computer-executable instructions to at least:

delete the first textual data of the first item of the electronic catalog.

5. A computer-implemented method comprising:

under control of a hardware computing device configured with specific computer-executable instructions,

receiving a first image associated with a first item from an electronic catalog comprising a plurality of items, wherein the first image comprises a first plurality of colors, wherein each item of the plurality of items is associated with an image and textual data that is descriptive of the item, and wherein the electronic catalog further comprises at least an inaccuracy where some textual data inaccurately describes the item;

retrieving first textual data associated with the first item;

obtaining a predetermined color palette comprising a second plurality of colors, the predetermined color palette associated with a second color palette name comprising second textual data;

determining a first color range based at least in part on a color threshold from a first color of the first plurality of colors in a color space, wherein the color space corresponds to a mathematical color model, and wherein the first color within the mathematical color model corresponds to a coordinate;

comparing the first color to a second color from the second plurality of colors, based at least in part on the second color being within the first color range, to determine that the first color corresponds to the second color, wherein comparing the first color to the second color further comprises;

calculating an integer search range, wherein calculating the integer search range further comprises interleaving bits from the first color range;

initiating a search of a data store based at least in part on a search query comprising the integer search range as a search parameter, the data store comprising a record associated with at least one indexed integer color value; and

receiving a search result from the data store, the search result comprising a first record associated with a first indexed integer color value for the second color;

comparing a third color from the first plurality of colors to a fourth color from the second plurality of colors to determine that the third color corresponds to the fourth color;

identifying the inaccuracy, wherein identifying the inaccuracy comprises;

comparing the first textual data and the second color palette name based at least on a textual comparison between the first textual data and the second textual data to determine a difference between the first textual data and the second palette color name; and

in response to identifying the inaccuracy, updating the first textual data of the first item of the electronic catalog to generate updated first textual data.

6. The computer-implemented method of claim 5, wherein the textual comparison comprises at least one of partial textual matching, textual matching, or natural language processing.

7. The computer-implemented method of claim 5, further comprising:

generating a user interface, wherein the user interface is configured to display the first image, the first textual data, and the second color palette name.

8. The computer-implemented method of claim 5, wherein the second color palette name corresponds to user input data.

9. The computer-implemented method of claim 5, further comprising:

determining a second color range based at least in part on a second color threshold from the third color in the color space, wherein comparing the third color to the fourth color further comprises determining that the fourth color is within the second color range.

10. The computer-implemented method of claim 5, further comprising:

generating a notification alert.

11. The computer-implemented method of claim 5, further comprising:

deleting the first textual data of the first item of the electronic catalog.

12. A non-transitory computer-readable storage medium storing computer executable instructions that when executed by a processor perform operations comprising:

receiving a first image associated with a first item from an electronic catalog comprising a plurality of items, wherein the first image comprises a first plurality of colors, wherein each item of the plurality of items is associated with an image and textual data that is descriptive of the item, and wherein the electronic catalog further comprises at least an inaccuracy where some textual data inaccurately describes the item;

retrieving first textual data associated with the first item;

obtaining a predetermined color palette comprising a second plurality of colors, the predetermined color palette associated with a second color palette name comprising second textual data;

determining a first color range based at least in part on a color threshold from a first color of the first plurality of colors in a color space, wherein the color space corresponds to a mathematical color model, and wherein the first color within the mathematical color model corresponds to a coordinate;

comparing the first color to a second color from the second plurality of colors, based at least in part on the second color being within the first color range, to determine that the first color corresponds to the second color, wherein comparing the first color to the second color further comprises;

calculating an integer search range, wherein calculating the integer search range further comprises interleaving bits from the first color range;

initiating a search of a data store based at least in part on a search query comprising the integer search range as a search parameter, the data store comprising a record associated with at least one indexed integer color value; and

receiving a search result from the data store, the search result comprising a first record associated with a first indexed integer color value for the second color;

comparing a third color from the first plurality of colors to a fourth color from the second plurality of colors to determine that the third color corresponds to the fourth color;

identifying the inaccuracy, wherein identifying the inaccuracy comprises;

comparing the first textual data and the second color palette name based at least on a textual comparison between the first textual data and the second textual data to determine a difference between the first textual data and the second palette color name; and

in response to identifying the inaccuracy, updating the first textual data of the first item of the electronic catalog to generate updated first textual data.

13. The non-transitory computer-readable storage medium of claim 12, wherein the textual comparison comprises at least one of partial textual matching, textual matching, or natural language processing.

14. The non-transitory computer-readable storage medium of claim 12, the operations further comprising:

generating a user interface, wherein the user interface is configured to display the first image, the first textual data, and the second color palette name.

15. The non-transitory computer-readable storage medium of claim 12, wherein obtaining the predetermined color palette is further based at least in part on voting data associated with the predetermined color palette.

16. The non-transitory computer-readable storage medium of claim 12, the operations further comprising:

comparing each remaining color from the first plurality of colors to a respective remaining color from the second plurality of colors.

17. The non-transitory computer-readable storage medium of claim 12, the operations further comprising:

determining a second color range based at least in part on a second color threshold from the third color in the color space, wherein comparing the third color to the fourth color further comprises determining that the fourth color is within the second color range.

18. The non-transitory computer-readable storage medium of claim 12, the operations further comprising:

deleting the first textual data of the first item of the electronic catalog.

19. The non-transitory computer-readable storage medium of claim 12, the operations further comprising generating a notification alert.

20. The non-transitory computer-readable storage medium of claim 12, the operations further comprising:

receiving user input data, wherein the updated first textual data comprises the user input data.